VOLUME 11, ISSUE 12, DECEMBER 2023

Abstract: The automobile sector across the globe has undergone a dramatic change in the last decade. It has started to trust something more, which initially was criticized for its inferior performance – the Electric Vehicle (EV). The battery is one of the most important components of an EV, and the Battery Management System (BMS) continues to be the bottleneck of EVs. However, accurate estimation of the State of Charge (SOC) of batteries is still challenging due to the non-linear characteristics of batteries. This led the scholars to propose various methods of SoC estimation. It now poses a challenge to establish a relationship between the accuracy and robustness of the methods, and their difficulties to implement. This paper publishes an exhaustive literature survey of the SoC estimation methods proposed by various scholars. All the more, it also provides feedback on each method, which will help to make an accurate choice of the SoC estimation method to be implemented. This will, in turn, help in the development of a reliable BMS.

Keywords: Battery Management System (BMS), State of Charge (SoC), Electric Vehicle (EV), Look-up table based estimation, model based estimation, adaptive system based estimation.

Abstract: People with disabilities and the aged can't do the whole lot themselves. So each and every time, they want anybody to do their job. Additionally, human beings might also now not experience at ease now and again coming near a swap to flip something on or off in their home. The essential aim was once to increase a utility that permits faraway manage of family home equipment and additionally offers protection towards incidents when the property owner is no longer at home. This article is in general about computerized managing of lights or any different domestic equipment the use of the Internet. This is about saving electrical strength and human energy. This app is created the usage of Internet of Things and Raspberry Pi. Different gadgets are related to the Raspberry Pi the usage of a Wi-Fi community or the Internet.

Keywords: Internet of Things, Raspberry Pi 4, Home automation, Server, Mobile devices.

Abstract: In this paper, a micro grid (MG) power generation system is interconnected with a single area reheat thermal power system for load frequency control study. A new heuristic optimization algorithm Grey wolf Optimization (GWO) algorithm is applied to evaluate optimal gains of the proportional integral and derivative (PID) controllers. The system dynamic performance is studied by comparing the results with GWO optimized PI/PID controllers. Also the system performance is investigated with PID controller optimized by recently developed grey wolf optimizer (GWO) algorithm, which has proven its superiority over other previously developed algorithm in many interconnected power systems.

Keywords: Micro grid, Load frequency control, Grey wolf optimization algorithm, PI/PID controllers.

Abstract: The Head motion controlled wheelchair is propelled by means of an electric motor rather than manually. Quadriplegics are one of the many physically disabled people that require such wheelchairs. They have paralysis of all four limbs and the torso that may be caused due to spinal cord injuries, strokes or cerebral palsy. They have no control over their hand movements and cannot grasp things or perform motions that might allow them independence over their movements. The tilting movements of the head in the four directions- forward, backward, right or left-would cause the wheelchair to move in the signaled directions. Quadriplegics rely on power wheelchairs for mobility, but the hands-free controller systems currently available are obtrusive and expensive. Smart wheelchair is an innovation that has an intention to create a difference for the activities of the people who are restricted by movement. This is an idea to ease those patients, who cannot perform hand movements in a way that can move a wheelchair. In this paper, we discuss about the working model of a head motion controlled wheelchair using Internet of things (IoT). The movement of the head is detected by MPU6050 and the signal is transmitted to the microcontroller. Then controller processes the signal and motion of wheelchair is enablesthe navigation. The wheelchair was capable of moving left, right, forward and backward direction and it is capable of doing tasks like navigation, obstacle detection, etc. using sensors and intelligence.

Keywords: Head motion, Quadriplegics, IoT, Wheelchair.

Abstract: In this paper we study design and development of AGVs, here we focuses on the overview on AGVS technology discusses recent technological developments to bring the automation in the Industries, Ports and many more places.

Keywords: ATMEGA 328, Software, AGVs, Material handling system, Automation.

Abstract: The demand for passenger vehicles has grown significantly over the past 20 years due to the world's population growth and the vehicle industry's rapid expansion. The energy used to burn fuel in a diesel engine is only 41 % turned into work that is useful for moving a car and its supplementary loads. The remaining heat is lost by radiation and convection from the engine block, as well as waste heat released by the exhaust system of the engine. This leads to a severe energy crisis and has an impact on the environment by increasing fuel usage. As much as 30 to 40% of exhaust gases with thermal energy released from internal combustion engines, reaching temperatures of 200 to 250 degrees Celsius, are released straight into the atmosphere. Utilizing the heat energy produced by an internal combustion engine is the project's objective. By doing so, the amount of fuel heat energy that is used by the internal combustion engine can be decreased, increasing the engine's efficiency. The task is to create a duct that can be altered to improve heat transfer and dissipate as much heat as possible to the TEG module's hot side. Additional fins can be incorporated into the duct's design to further enhance heat transfer.

Abstract: Light Fidelity (Li-Fi) is an innovative technology that revolves around communication through the utilization of the visible light spectrum. Li-Fi primarily employs existing light sources, such as LEDs, to convey data by modulating the LED's light output. A photodetector device, capable of detecting changes in light intensity, receives and interprets the transmitted data. Consequently, this technology achieves dual purposes: illumination and communication simultaneously.

The present project involves the practical implementation of Li-Fi, where data is transmitted up to a distance of 2 - 3 meter, achieving a data rate of 115200 bits per second with a speed of 14 kbps.

Keywords: LED, Li-Fi, Visible light communication, Alternating current, Direct current, Printed circuit board.

Abstract: Lithium, a remarkably reactive metal, finds extensive applications in rechargeable batteries for electric vehicles and portable electronics owing to its exceptional energy density. The extraction of lithium encompasses a range of technologies that are contingent on the source. In the case of lithium brine deposits, the prevalent approach involves evaporation, where brine is introduced into expansive evaporation ponds, facilitating the gradual evaporation of water and the consequent concentration of lithium-rich salts. As for hard rock lithium deposits, they are extracted through open- pit or underground mining, followed by a sequence of crushing and flotation processes to procure lithium concentrate. Moreover, groundbreaking methods, such as the direct extraction of lithium from geothermal brines and the recovery of lithium from seawater, are actively under exploration to cater to the surging demand for this invaluable resource.

Abstract: A biogas leakage detection service needs to be included in the continuous maintenance routine of every competent plant operator. In addition, biogas includes hydrogen sulphide (H2S), a hazardous gas that has been responsible for several fatalities in the agricultural sector of the United Kingdom; these deaths have been attributed to the management of slurry tanks. Because hydrogen sulphide is heavier than air, it will accumulate on the ground. It has the potential to build up in tight places that have inadequate ventilation, and it may go undiscovered until someone enters the space, which may have potentially catastrophic consequences. To detect gas leakage, an Internet of Things (IoT) enabled gas leakage detection system is an intelligent method. Leakage of gas is a significant safety hazard in a variety of settings, including households, industries, and piped gas distribution networks. The most significant businesses that are susceptible to fire hazards include refineries, oil and gas industries, and supply-chain companies that deal with flammable gases and liquids.

Keywords: IoT, Biogas, Sensors, Gas Sensor, Leakage Detecting Device

Abstract: Modern renewable energy education is being reshaped by the proliferation of generative AI technologies, cloud computing, and related tools. This paper investigates contemporary topics and trends regarding the intersection of these technologies and renewable energy area, focusing on education and research. Concepts are introduced and discussed continually, and the related challenges and technical concerns are framed around transparency, equity, saturation, validity, quality, and model sizes. The identified education and research themes in the field are listed and organized, and a survey grounded on them is compared with existing initiatives. A suite of systems and portals designed and constructed to address existing gaps is described. These executive systems are informed and guided by a series of questions regarding modes of engagement, expectations on results and generated outputs, and requirements regarding transparency and branding. The delivery mechanisms, both recurrent and ad-hoc during the academic lifecycle, are summarized. Cloud architecture, implementation details regarding popular APIs and generative design platforms, and applied Software Engineering guidelines are also presented, in order to ease the use of the discussed solutions and approaches, and help in the design, development, and implementation of new solutions. Notable academic projects and creative industries are also mentioned and reviewed, and future directions and projects are outlined, regarding the application of prompts, and the consideration of dependency on architecture exposed by recent publications on the topic.

Keywords: Generative AI, cloud-based tools, renewable energy education, digital learning platforms, AI-driven content creation, interactive simulations, real-time data analysis, personalized learning, smart grid education, machine learning, energy forecasting, remote labs, scalable infrastructure, virtual classrooms, adaptive learning systems, data visualization, educational technology, sustainable energy training, cloud computing, intelligent tutoring systems.

Abstract: In the realm of modern retail operations, agility is paramount to addressing rapidly changing market demands and consumer expectations. Traditional operational support systems often struggle to keep pace with these dynamic environments, necessitating a transformative approach. Enhancing retail infrastructure agility through intelligent operational support systems and machine learning-orchestrated workflows presents a promising solution. This text explores how integrating advanced technologies such as artificial intelligence and machine learning into retail operational support systems can streamline processes, optimize resource allocation, and ultimately boost the overall efficiency of retail infrastructures.
The introduction of intelligent operational support systems redefines the traditional retail operational framework, offering capabilities that extend beyond basic system support functions. These systems, equipped with advanced algorithms, provide real-time data processing, predictive analytics, and autonomous adjustments that are instrumental in decision- making processes. By leveraging machine learning, retailers can orchestrate workflows that automatically adapt to fluctuating demands and optimize inventory management while minimizing human intervention and operational bottlenecks. This not only enhances agility within supply chains but also empowers retailers to offer personalized customer experiences by understanding consumer behaviors and preferences with greater precision.
Furthermore, the adoption of machine learning-orchestrated workflows facilitates a more proactive retail strategy, allowing organizations to anticipate market trends and respond swiftly to external disruptions. It fosters a data-driven culture where insights are continuously derived from intricate datasets, enabling strategic planning and nimble execution. As retail establishments evolve into complex ecosystems, the intelligent operational support systems framework emerges as a critical component for sustaining competitive advantage and driving sustainable growth. This text argues that the integration of these technologies into retail infrastructures is not merely beneficial but essential for remaining relevant and resilient in a fluctuating global market.

Keywords: Retail Infrastructure,Operational Support Systems (OSS),Machine Learning (ML),Workflow Automation,Infrastructure Agility,Intelligent Operations,Digital Transformation,Predictive Analytics,Retail Technology,AI-Driven Workflows,Service Orchestration,Cloud-native OSS,Network Optimization,Real-time Monitoring,Scalable Retail Solutions.

Abstract: The advancement of artificial intelligence and machine learning has revolutionized risk assessment in the auto and property insurance markets, providing dynamic capabilities to predict, evaluate, and mitigate risks more effectively than traditional methods. This paper presents an exploration of how AI and ML technologies can significantly enhance insurers' ability to assess risks dynamically, thereby transforming underwriting practices, customer experiences, and overall operational efficiencies. Unlike static models that rely heavily on historical data, sophisticated algorithms can process vast volumes of real-time data, adapting to emerging patterns and anomalies that may affect risk profiles.

The integration of AI and ML into risk assessment processes empowers insurers to leverage predictive analytics, deriving insights that improve decision-making accuracy. For instance, in auto insurance, telematics combined with AI allows for refined driver behavior analysis, adjusting premiums based on real-time driving patterns rather than generic demographic information. Similarly, ML models in property insurance utilize data from various sources, including IoT devices and satellite imagery, to dynamically update risk assessments for properties based on environmental changes and historical weather patterns. Such capabilities not only enhance precision but also foster proactive risk management.

Moreover, the implementation of AI and ML introduces a paradigm shift towards personalization in insurance products and services, aligning closely with individual risk factors and preferences. The predictive power of these technologies facilitates the identification of potential fraud, optimizing claims processing and reducing operational costs. However, the adoption of AI-driven risk assessment also brings challenges, including data privacy concerns and the need for robust regulatory frameworks to govern AI applications in insurance. This analysis underscores the need for insurers to balance technological advancement with ethical considerations and regulatory compliance to leverage AI's full potential responsibly. This comprehensive evaluation highlights the transformative impact of AI and ML in reshaping the landscape of dynamic risk assessment in the insurance sector.

Keywords: AI-driven risk modeling,Machine learning insurance analytics,Predictive underwriting models,Telematics data analysis,Real-time risk assessment,Property damage prediction,Automated claims processing,Fraud detection algorithms,Behavioral risk profiling,Geo-spatial risk modeling,Climate risk analytics,Dynamic pricing algorithms,Smart sensor data integration,Insurance AI decision support,Claims severity prediction.

Abstract: Leveraging Artificial Intelligence for Strategic Decision-Making in Tax Administration and Policy Design presents Artificial Intelligence (AI) – both its opportunities and uncertain consequences – within the sphere of public tax administration. We show how tax administration, as a strategic operator of AI, can draw from its traditional managerial methods and management sciences to augment the ability of AI to decide strategically in the design of tax policy and the creation and manipulation of incentives and payoffs that motivate taxpayer decisions. AI has arrived at the doorstep of a techno-economic moment that has knock-on effects affecting the very pillars of society. We argue that it is the task of decision-makers to leverage AI but also to ask themselves – are there questions with uncertain answers that AI cannot help us with? As new models of machines and services become available to help us navigate our environment, AI capable of doing strenuous and difficult work without pause becomes a partner for innovation and decision-making. Exploring the explication of large recognitive models, we highlight the implications of AI for tax administration business processes, and for key areas of operations. The joint distribution of discrete data policies implicitly suffices to reflect the multi- routing of communications and identifying agent principals, including transactions and interactions in a digital landscape where digital profiling predicts and infers possible agent actions – buying, selling, manipulating, cheating. Lessons from current AI models serving image processing or vector classification become incredible platforms for new risk management workflows. However, supplementing AI Risk Assessment models, management must prepare and maintain an intuitive feel for reality and collective unpredictability, the very characteristics that distinguish human strategic thinking and decision-making from machines – that model all the inductive and deductive relationships and their distribution through a holdout remainder set.

Keywords: Artificial Intelligence, Strategic Decision-Making, Tax Administration, Policy Design, Data Analytics, Machine Learning, Predictive Modeling, Automation, Risk Assessment, Tax Compliance, Revenue Forecasting, Fraud Detection, Natural Language Processing, Data-Driven Insights, Real-Time Monitoring, Taxpayer Behavior, Decision Support Systems, Algorithmic Optimization, Policy Simulation, Digital Transformation, Tax System Efficiency, AI Governance, Intelligent Systems, Behavioral Analytics, Public Sector Innovation, Regulatory Compliance.

Abstract: Artificial Intelligence (AI) is positioned to transform healthcare services and operations into intelligent systems, delivering innovative solutions to improve the quality of care while containing rising costs. However, AI readiness at all levels of the healthcare ecosystem must be examined in combination with real-world implementations that deliver actual transformation. Readiness is commonly defined as the state of being fully prepared for something. In a healthcare management context, readiness refers to the state of a healthcare organization in determining whether the required capabilities exist for the successful adoption of a new technology or concept. Towards AI integration in healthcare, the concept applies at three levels—technological, data, and skills readiness—and can be assessed using maturity frameworks that provide an indication of progress and direction, as well as stakeholder analysis.

While Technology Adoption Models assess potential uptake of AI solutions by health practitioners, these validations assess preparedness to adopt and/or innovate in AI solutions within the healthcare ecosystem. Emerging AI applications covering clinical needs from radiology to mental health support, or from product development to operational management, present recognition and acceptance challenges requiring stakeholder engagement. Stakeholder impact on the success of AI solutions can be assessed using readiness levels, grouping stakeholders into three categories: IDPC leaders responsible for implementation, users at the point of care who interact directly with patients, and patients, the users of the healthcare system and the ultimate beneficiaries or sufferers from the role out of the AI solution.

Keywords: AI readiness assessment, Digital health infrastructure,Clinical workflow integration,Health data interoperability,Electronic health record (EHR) maturity,Data governance frameworks,Ethical AI in healthcare,Workforce AI competency,Change management in healthcare,Clinical decision support systems,Health information security,Regulatory compliance for AI,Algorithm transparency,Patient data quality,Organizational readiness for AI,AI adoption barriers,Health system innovation capacity,Human–AI collaboration,AI-enabled care delivery,Implementation science for AI in healthcare.

Abstract: Over the past decade, claims processing has emerged as a primary area of interest for insurers exploring how artificial intelligence (AI) can reduce costs or enhance service quality. Several factors motivate this focus. First, processing claims represents a major operational expense—one that, if reduced, is likely to translate into greater profitability. Second, claims processing often significantly influences the customer experience and may even determine clients’ future purchase decisions. Finally, AI technologies tailored for claims processing have demonstrated the ability to deliver faster settlement of smaller claims without sacrificing accuracy. Provided that AI is applied within a carefully monitored, ethically governed framework, its integration into claims processing represents a genuine win-win opportunity.

But increasing the efficiency of claims processing is only half the story. Unless these savings translate into improved customer experience and satisfaction, the long-term gains may be illusory. Customers today demand – and expect – faster claims settlements. Organisations that can consistently meet these expectations are likely to enjoy a competitive edge, gaining not only customer satisfaction but also long-term loyalty. Conversely, companies that fail to deliver speedy settlements will, over time, see an increased rate of customer attrition, particularly among their high-value clients. Insurers that can harness new AI capabilities to manage these twin objectives – faster settlement with greater consistency – stand to capture both the operating and customer experience benefits.

Keywords: Artificial Intelligence In Insurance, Automated Claims Processing, Insurance Operations Optimization, Cost Reduction Strategies, Customer Experience Enhancement, Claims Settlement Acceleration, Ethical AI Governance, AI- Driven Decision Support, Small Claims Automation, Operational Efficiency Gains, Customer Satisfaction Management, Competitive Advantage In Insurance, Claims Accuracy And Consistency, Service Quality Improvement, Customer Retention And Loyalty, High-Value Client Management, Digital Insurance Transformation, AI Monitoring And Oversight, Intelligent Claims Workflows, Experience-Driven Insurance Services.

Abstract: Research into cloud-based AI-driven personalized learning offers insights into the defining concepts, properties, enabling technologies, methodologies, and challenges that characterize this rapidly-developing area. AI- driven personalized learning adapts to individual learners, fostering growth and engagement through analysis of extensive personal and behavioral data. Cloud computing affords the necessary scalable infrastructure for such platforms while meeting the requirements for data storage and processing in educational AI. Unifying System Theory suggests a natural evolution through levels of system integration, combining AI-driven learning in the cloud with crowd-powered content in a modularized, interoperable structure.

Adaptive education provides the theoretical foundations for personalized learning; however, student modeling, recommendation, and natural language processing remain prevalent areas for investigation. Quality and evaluation are equally important, encompassing experimental design and validation in AI-supported cloud ecosystems, along with considerations of bias, fairness, and transparency. Security, privacy, and compliance aspects of personalized learning in the cloud, including identity and data protection, risk management, auditing, and adherence to privacy frameworks such as FERPA, also warrant rigorous scrutiny.

Keywords: AI, Personalized Learning, Adaptive Learning, Cloud Computing, Technology Enhanced Learning, Educational Data Mining, Learning Analytics, Recommender Systems, Learning-as-a-Service, Learning Management System, Natural Language Processing, Evidence-based Education, Online Learning, Educational Technology, Cloud Computing, Educational Technology Evaluation, Process Mining, Artificial Intelligence in Education.

Abstract: Data engineering refers to the set of activities related to preparing and managing data for analytical workloads, and it encompasses a wide range of tasks performed on data at different stages of the analytics life cycle—from ingestion and integration to feature engineering and metadata management. A data engineering pipeline connects various e- commerce data sources by combining data from multiple operational silos (product catalog, customer accounts, shopping carts, transaction records, shipping and delivery, payments, etc.) in order to support the development of artificial intelligence models used for personalized website experiences, recommendation engines, dynamic pricing strategies, and demand forecasting. Nowadays, the volume of consumed data and the highly dynamic nature of the business logic being implemented in the underlying model have reached a point where data engineering pipelines need to be automated, enabling the data operations teams to support the business more efficiently.

Automation at scale is an ambitious goal that requires specialized frameworks and technologies across different areas of data engineering. These areas are outlined through recurring architectural patterns, and each pattern is built by assembling the most suitable services and tools on the market from the cloud providers that best match the organization’s business requirements in order to enable the core automation processes. Reusable building blocks are introduced for key activities such as cloud-native data platforms, data orchestration and workflow automation, automated schema discovery and adaptation, and anomaly detection and data quality alerting. Even though these solutions are presented in the context of personalized experiences and recommendation engines—typical workloads of any large e-commerce organization—they cover only part of the actual automation. The presented approaches can be applied to any AI/ML problem requiring a data plane—such as dynamic pricing and demand forecasting—with the required effort range for implementation.

Keywords: Data Engineering, Automation, AI, E-Commerce, Personalization,Automated Data Pipelines,AI-Driven ETL / ELT,Real-Time Data Processing,E-Commerce Data Integration,Data Quality Monitoring,Intelligent Data Orchestration,Predictive Data Validation,Customer Behavior Analytics,Scalable Cloud Data Warehousing,Anomaly Detection in Data Streams.

Abstract: Rare diseases present a unique diagnostic challenge. With only a handful of identified cases and wide-ranging clinical manifestations, these diseases rarely appear in the differential diagnosis of physician decision-support systems. Consequently, they are infrequently considered at the initial visit. Lack of awareness thus leads to severe, irreversible complications, considerable impairment or even death, ultimately resulting in a loss of human life comparable to that of common diseases like breast cancer. A real-time diagnostic service for several rare diseases—stargardt disease, idiopathic pulmonary fibrosis, systemic lupus erythematosus, scleroderma, Crohn disease, and Cushing syndrome—based on federated learning and cloud artificial intelligence can help overcome the problem. The objective of the federated-learning service is to train an artificial-intelligence model at each hospital site without collecting or sharing sensitive data in a central cloud. The multi-institutional architecture is designed to produce collaborative real-time diagnoses without the large time lags associated with multisite diagnosis requested from typical cloud-based platforms.
The proposed research framework guarantees that highly sensitive data from different locations remains on-site during the training process, can receive real-time predictions through the AI model of other sites, and thus supports local specialists in correctly diagnosing rare diseases. A federated approach minimizes the potential presence of low-quality data and enhances the diagnostic reliability of models used to support the decision-making process. Given the richness of medical data from different areas supplied by different medical centers, the approach is applicable across a broad range of federated-learning scenarios.

Keywords: Rare Disease Diagnosis, Federated Learning in Healthcare, Privacy-Preserving Medical AI, Distributed Clinical Decision Support, Real-Time Diagnostic Services, Multi-Institutional AI Architectures, Collaborative Model Training, Sensitive Medical Data Protection, Cloud-Based Artificial Intelligence, Federated Diagnostic Frameworks, Clinical Decision Support Systems (CDSS), Cross-Site Medical Learning, Diagnostic Reliability Enhancement, Low- Prevalence Disease Detection, Medical Data Heterogeneity, Secure AI Model Exchange, Hospital-Based AI Deployment, Federated Prediction Services, Trustworthy Medical AI, Scalable Federated Healthcare Systems.